Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to recent academic papers and textbooks related to scientific theories and problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endar
    -0.07
    ICAST
    -0.07
     ún
    -0.06
    aphael
    -0.06
    деÑĢж
    -0.06
    ãĥ³ãĥķ
    -0.06
    ostel
    -0.06
    ningen
    -0.06
    endum
    -0.06
    imler
    -0.06
    POSITIVE LOGITS
     book
    0.16
     review
    0.15
     reviews
    0.15
    reviews
    0.13
    review
    0.13
     Review
    0.12
     books
    0.12
    book
    0.12
    -review
    0.12
    _reviews
    0.12
    Act Density 0.082%

    No Known Activations